rkzed

joined 1 year ago
sorted by: new top controversial old
Maybe anecdotal but I have very high hopes for Yi 34b finetunes. in c/localllama@poweruser.forum
[–] rkzed@alien.top 1 points 11 months ago

I had great fun with this specific model. Tried up to 32K context length with very minimum repetition problem..

New Model: openchat 3.5 with 16k context in c/localllama@poweruser.forum
[–] rkzed@alien.top 1 points 1 year ago (3 children)

I'm confused with their prompt format, do we really need to use their library to try the model?

Question about the 'economics' of running a LLM locally? in c/localllama@poweruser.forum
[–] rkzed@alien.top 1 points 1 year ago

if i just want to try big models, renting is more reasonable. but if i plan to use it daily and for the longer period of time, making investment to buy the GPU is make a lot of sense. not only you could use the GPU for gaming or another tasks, you also actually own the GPU which you could probably sell it later for minimum half the original price.